Skip to contents

Read and process data with subsets and variables

Source: R/mentry.R
mentry.Rd

The input data gets processed based on TRT, BY and/or SUBGROUP variables and filtered by subset conditions. This processed data flows into categorical and numerical utilities such as mcatstat() and msumstat() for further analysis.

Usage

mentry(
  datain,
  subset = NA,
  byvar = NA,
  subgrpvar = NA,
  trtvar = NA,
  trtsort = NA,
  trttotalyn = "N",
  trttotlabel = "Total",
  trtmissyn = "N",
  sgtotalyn = "N",
  add_grpmiss = "N",
  pop_fil = "Overall Population"
)

Arguments

datain

Input dataset can be any ADaM data.

subset

Subset conditions for analysis of dependent variable.

byvar

Tilde(~) separated strings for grouping variable names. Assigns to BYVAR1, BYVAR2, etc. Use '/' to specify ordering variables. eg: SEX/SEXN~COUNTRY.`

subgrpvar

Tilde(~) separated strings for grouping variable names. Assigns to SUBGRPVAR1, SUBGRPVAR2, etc. Use '/' to specify ordering variables. eg: RACE/RACEN~ETHNIC.

trtvar

Treatment variable name string assigned as TRTVAR.

trtsort

Treatment sorting variable name string - numeric or character variable assigned as TRTSORT.

trttotalyn

Add total treatment values to be displayed as column in table or category in plot ("Y"/"N").

trttotlabel

Label for total Treatment column/group

trtmissyn

Retain Missing treatment counts in Total (if trttotalyn = Y). Missing treatment will not be considered as a column in analysis in any case.

sgtotalyn

Add total subgroup values to be displayed as column in table or category in plot ("Y"/"N").

add_grpmiss

Add row or column for missing category in grouping variables. ("Y"/"N")

pop_fil

Population Filter for data set: Name of flag variable. eg: "SAFFL", "EFFFL" or NA for Overall Population.

Value

a data.frame output to be used in further utilities with applied subset

Details

  1. By Variable Processing Identify byvars if byvar is given, create BYVAR1, BYVAR2, etc. Check for numeric code list variable for the grouping var, if not create numeric variable for sorting as BYVAR1N, BYVAR2N etc. Convert to character if numeric. Re-code blanks from grouping variables as "Missing" Remove missing category value from grouping variable per user choice.

  2. Treatment Variable Processing Identify Treatment Variable, treatment sorting variable. Remove non treatment values. If treatment sort variable doesn't exist, make it same as TRTVAR If treatment sort is not numeric, convert to numeric Add treatment total column based on trttotalyn Convert TRTVAR to a factor in same order as TRTSORT

  3. Subgroup Variable processing Identify Subgroup variable: create SUBGRPVAR1N, SUBGRPVAR2N etc if subgrpvar is specified. Check presence of numeric code list variables for the subgroup variables, if not create numeric variable for sorting purpose as SUBGRPVAR1N etc Re-code blanks from By and Subgroup vars as Missing Remove missing category value from grouping variable per user choice Add Subgroup total column for the last subgroup variable

  4. Subset Processing Applying population subset selected Applying denominator/overall subset condition passed by the user Applying analysis subset condition passed by the user

  5. Calculate Big N for displaying in final output data.frame with Count N for each treatment/subgroup if they exist. If no Big N required, then NA is returned.

Examples

data(adsl)

df_mentry <-
  adsl |> mentry(
    subset = "EFFFL=='Y'",
    byvar = "SEX/SEXN~AGEGR1",
    trtvar = "TRT01A",
    trtsort = "TRT01AN",
    subgrpvar = "RACE/RACEN~BMIBLGR1",
    trttotalyn = "N",
    add_grpmiss = "N",
    sgtotalyn = "N",
    pop_fil = "Overall Population"
  )

df_mentry
#> # A tibble: 234 × 58
#>    STUDYID     USUBJID SUBJID SITEID SITEGR1 ARM   TRT01P TRT01PN TRT01A TRT01AN
#>    <chr>       <chr>   <chr>  <chr>  <chr>   <chr> <chr>    <dbl> <chr>    <dbl>
#>  1 CDISCPILOT… 01-701… 1015   701    701     Plac… Place…       0 Place…       0
#>  2 CDISCPILOT… 01-701… 1023   701    701     Plac… Place…       0 Place…       0
#>  3 CDISCPILOT… 01-701… 1028   701    701     Xano… Xanom…      81 Xanom…      81
#>  4 CDISCPILOT… 01-701… 1033   701    701     Xano… Xanom…      54 Xanom…      54
#>  5 CDISCPILOT… 01-701… 1034   701    701     Xano… Xanom…      81 Xanom…      81
#>  6 CDISCPILOT… 01-701… 1047   701    701     Plac… Place…       0 Place…       0
#>  7 CDISCPILOT… 01-701… 1097   701    701     Xano… Xanom…      54 Xanom…      54
#>  8 CDISCPILOT… 01-701… 1111   701    701     Xano… Xanom…      54 Xanom…      54
#>  9 CDISCPILOT… 01-701… 1115   701    701     Xano… Xanom…      54 Xanom…      54
#> 10 CDISCPILOT… 01-701… 1118   701    701     Plac… Place…       0 Place…       0
#> # ℹ 224 more rows
#> # ℹ 48 more variables: TRTSDT <date>, TRTEDT <date>, TRTDUR <dbl>, AVGDD <dbl>,
#> #   CUMDOSE <dbl>, AGE <dbl>, AGEGR1 <chr>, AGEGR1N <dbl>, AGEU <chr>,
#> #   RACE <chr>, RACEN <dbl>, SEX <chr>, ETHNIC <chr>, SAFFL <chr>, ITTFL <chr>,
#> #   EFFFL <chr>, COMP8FL <chr>, COMP16FL <chr>, COMP24FL <chr>, DISCONFL <chr>,
#> #   DSRAEFL <chr>, DTHFL <chr>, BMIBL <dbl>, BMIBLGR1 <chr>, HEIGHTBL <dbl>,
#> #   WEIGHTBL <dbl>, EDUCLVL <dbl>, DISONSDT <date>, DURDIS <dbl>, …